Voice-controlled assistant volume control

• US 10,891,946 B2
• Filed: 07/28/2016
• Issued: 01/12/2021
• Est. Priority Date: 07/28/2016
• Status: Active Grant

• Current Assignee: Red Hat, Inc. (International Business Machines Corporation)
• Original Assignee: Red Hat, Inc. (International Business Machines Corporation)
• Inventors: Pechanec, Jiri, Vecera, Martin
• Primary Examiner(s): Armstrong, Angela A
• Application Number:
  US15/221,869
• Publication Number:
  US 20180033424A1
• Time in Patent Office: 1,629 Days
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/225 Feedback of the input speech
• CPC Class Codes: G10L 21/0364 for improving intelligibility
• CPC Class Codes: H03G 3/02 Manually-operated control H03G3/001 and H03G3/002 take precedence
• CPC Class Codes: H03G 3/3005 in amplifiers suitable for low-frequencies, e.g. audio amplifiers H03G3/32, H03G3/34 take precedence
• CPC Class Codes: H03G 3/32 the control being dependent upon ambient noise level or sound level

Abstract

A method includes receiving a voice command, determining, by a processing device, a first loudness parameter associated with the voice command, generating a voice response to the voice command, and determining a target loudness parameter associated with the voice response in view of the first loudness parameter associated with the voice command.

Claims

1. A method comprising:

receiving a voice command;

determining, by a processing device, a first loudness parameter associated with the voice command;

determining a second loudness parameter associated with a background noise;

generating a voice response to the voice command;

determining a target loudness parameter associated with the voice response, wherein the target loudness parameter is less than the first loudness parameter and greater than the second loudness parameter, such that the target loudness parameter is greater than a noise level of the background noise and less than a noise level of the voice command;

generating, by an acoustic signal output device, a sound signal of the voice response;

determining a third loudness parameter of the sound signal generated by the acoustic signal output device;

calculating a difference between the target loudness parameter and the third loudness parameter of the sound signal;

regulating a volume of the sound signal in view of the difference using a proportional-integral-differential (PID) controller; and

causing output of the sound signal of the voice response at the volume in view of the target loudness parameter and the difference.

2. The method of claim 1, wherein determining the target loudness parameter comprises determining the target loudness parameter at a level not exceeding the first loudness parameter associated with the voice command.

3. The method of claim 1, wherein the voice command is an activation command for a voice-controlled assistant application executing on the processing device.

4. The method of claim 1, wherein determining the first loudness parameter associated with the voice command comprises determining a sound pressure of the voice command received at an acoustic input device.

5. The method of claim 1, further comprising:

converting the voice command into a natural language text;

parsing the natural language text to identify a task requested by a user; and

generating, by a voice-controlled assistant, the voice response in view of the task.

6. The method of claim 1, wherein the first loudness parameter is determined in view of a first sound pressure associated with the received voice command and wherein the second loudness parameter is determined in view of a second sound pressure associated with the background noise.

7. A system comprising:

an acoustic signal input device to receive a voice command;

a processing device, communicatively coupled to the acoustic signal input device, the processing device to;

determine a first loudness parameter associated with the voice command;

determine a second loudness parameter associated with a background noise;

generate a voice response to the voice command;

determine a target loudness parameter associated with the voice response, wherein the target loudness parameter is less than the first loudness parameter and greater than the second loudness parameter, such that the target loudness parameter is greater than a noise level of the background noise and less than a noise level of the voice command;

an acoustic signal output device;

a sensor to determine a third loudness parameter of a sound signal generated by the acoustic signal output device;

a circuit to calculate a difference between the target loudness parameter and the third loudness parameter of the sound signal; and

a proportional-integral-differential (PID) controller to regulate a volume of the sound signal in view of the difference, wherein the acoustic signal output device to generate the sound signal of the voice response in view of the target loudness parameter and the difference.

8. The system of claim 7, wherein to determine the target loudness parameter, the processing device is further to determine the target loudness parameter at a level not exceeding the first loudness parameter associated with the voice command.

9. The system of claim 7, wherein the processing device is further to:

convert the voice command into a natural language text;

parse the natural language text to identify a task requested by a user; and

generate, by a voice-controlled assistant, the voice response in view of the task.

10. A computer-readable non-transitory medium stored thereon codes that, when executed by a processing device, cause the processing device to:

receive a voice command;

determine, by the processing device, a first loudness parameter associated with the voice command;

determine a second loudness parameter associated with a background noise;

generate a voice response to the voice command;

determine a target loudness parameter associated with the voice response, wherein the target loudness parameter is less than the first loudness parameter and greater than the second loudness parameter, such that the target loudness parameter is greater than a noise level of the background noise and less than a noise level of the voice command;

generate, by an acoustic signal output device, a sound signal of the voice response;

determine a third loudness parameter of the sound signal generated by the acoustic signal output device;

calculate a difference between the target loudness parameter and the third loudness parameter of the sound signal;

regulate a volume of the sound signal in view of the difference using a proportional-integral-differential (PID) controller; and

cause output of the sound signal of the voice response at the volume in view of the target loudness parameter and the difference.

11. The computer-readable non-transitory medium of claim 10, wherein to determine the target loudness parameter, the processing device is further to determine the target loudness parameter at a level not exceeding the first loudness parameter associated with the voice command.

12. The computer-readable non-transitory medium of claim 10, wherein the voice command is an activation command for a voice-controlled assistant application executing on the processing device.